Search

Quality-related prediction in the continuous-casting process is important for the quality and process control of casting slabs. As intelligent manufacturing technologies continue to evolve, numerous data-driven techniques have been available for industrial applications. This case study was aimed at developing a machine-learning algorithm, capable of predicting slag inclusion defects in continuous-casting slabs, based on process condition sensor data. A large dataset consisting of sensor data from nearly 7300 casting samples has been analyzed, with the empirical mode decomposition (EMD) algorithm utilized to process the multi-modal time series. The following machine-learning algorithms have been examined: K-Nearest neighbors, support vector classifier (linear and nonlinear kernels), decision trees, random forests, AdaBoost, and Artificial Neural Networks. Four over-sampling or under-sampling algorithms have been adopted to solve imbalanced data distribution. In the experiment, the optimized random forest outperformed other machine-learning algorithms in terms of recall and ROC AUC, which could provide valuable insights for quality control. [ABSTRACT FROM AUTHOR]

Federated learning has attracted much attention in fault diagnosis since it can effectively protect data privacy. However, efficient fault diagnosis performance relies on the uninterrupted training of model parameters with massive amounts of perfect data. To solve the problems of model training difficulty and parameter negative transfer caused by data corruption, a novel cross-device fault diagnosis method based on repaired data is proposed. Specifically, the local model training link in each source client performs random forest regression fitting on the fault samples with missing fragments, and then the repaired data is used for network training. To avoid inpainting fragments to produce the wrong characteristics of faulty samples, joint domain discrepancy loss is introduced to correct the phenomenon of parameter bias during local model training. Considering the randomness of the overall performance change brought about by the local model update, an adaptive update is proposed for each round of global model download and local model update. Finally, the experimental verification was carried out in various industrial scenarios established by three sets of bearing data sets, and the effectiveness of the proposed method in terms of fault diagnosis performance and data privacy protection was verified by comparison with various currently popular federated transfer learning methods. [ABSTRACT FROM AUTHOR]

This study proposes an approach to minimize the maximum makespan of the integrated scheduling problem in flexible job-shop environments, taking into account conflict-free routing problems. A hybrid genetic algorithm is developed for production scheduling, and the optimal ranges of crossover and mutation probabilities are also discussed. The study applies the proposed algorithm to 82 test problems and demonstrates its superior performance over the Sliding Time Window (STW) heuristic proposed by Bilge and the Genetic Algorithm proposed by Ulusoy (UGA). For conflict-free routing problems of Automated Guided Vehicles (AGVs), the genetic algorithm based on AGV coding is used to study the AGV scheduling problem, and specific solutions are proposed to solve different conflicts. In addition, sensors on the AGVs provide real-time data to ensure that the AGVs can navigate through the environment safely and efficiently without causing any conflicts or collisions with other AGVs or objects in the environment. The Dijkstra algorithm based on a time window is used to calculate the shortest paths for all AGVs. Empirical evidence on the feasibility of the proposed approach is presented in a study of a real flexible job-shop. This approach can provide a highly efficient and accurate scheduling method for manufacturing enterprises. [ABSTRACT FROM AUTHOR]